scholarly journals FASSD: A Feature Fusion and Spatial Attention-Based Single Shot Detector for Small Object Detection

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1536
Author(s):  
Deng Jiang ◽  
Bei Sun ◽  
Shaojing Su ◽  
Zhen Zuo ◽  
Peng Wu ◽  
...  
Keyword(s):  
Object Detection ◽  
Spatial Attention ◽  
Feature Fusion ◽  
Single Shot ◽  
Small Object ◽  
Feature Maps ◽  
Feature Representations ◽  
Small Object Detection ◽  
High Level ◽  
Detection Speed

Deep learning methods have significantly improved object detection performance, but small object detection remains an extremely difficult and challenging task in computer vision. We propose a feature fusion and spatial attention-based single shot detector (FASSD) for small object detection. We fuse high-level semantic information into shallow layers to generate discriminative feature representations for small objects. To adaptively enhance the expression of small object areas and suppress the feature response of background regions, the spatial attention block learns a self-attention mask to enhance the original feature maps. We also establish a small object dataset (LAKE-BOAT) of a scene with a boat on a lake and tested our algorithm to evaluate its performance. The results show that our FASSD achieves 79.3% mAP (mean average precision) on the PASCAL VOC2007 test with input 300 × 300, which outperforms the original single shot multibox detector (SSD) by 1.6 points, as well as most improved algorithms based on SSD. The corresponding detection speed was 45.3 FPS (frame per second) on the VOC2007 test using a single NVIDIA TITAN RTX GPU. The test results of a simplified FASSD on the LAKE-BOAT dataset indicate that our model achieved an improvement of 3.5% mAP on the baseline network while maintaining a real-time detection speed (64.4 FPS).

scholarly journals Small Object Detection in Traffic Scenes Based on Attention Feature Fusion

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3031
Author(s):  
Jing Lian ◽  
Yuhang Yin ◽  
Linhui Li ◽  
Zhenghao Wang ◽  
Yafu Zhou
Keyword(s):  
Object Detection ◽  
Feature Fusion ◽  
Contextual Information ◽  
Detection Accuracy ◽  
Small Object ◽  
Limited Information ◽  
Feature Maps ◽  
Multi Scale ◽  
Validation Set ◽  
Small Object Detection

There are many small objects in traffic scenes, but due to their low resolution and limited information, their detection is still a challenge. Small object detection is very important for the understanding of traffic scene environments. To improve the detection accuracy of small objects in traffic scenes, we propose a small object detection method in traffic scenes based on attention feature fusion. First, a multi-scale channel attention block (MS-CAB) is designed, which uses local and global scales to aggregate the effective information of the feature maps. Based on this block, an attention feature fusion block (AFFB) is proposed, which can better integrate contextual information from different layers. Finally, the AFFB is used to replace the linear fusion module in the object detection network and obtain the final network structure. The experimental results show that, compared to the benchmark model YOLOv5s, this method has achieved a higher mean Average Precison (mAP) under the premise of ensuring real-time performance. It increases the mAP of all objects by 0.9 percentage points on the validation set of the traffic scene dataset BDD100K, and at the same time, increases the mAP of small objects by 3.5%.

Improved YOLOv3 with duplex FPN for object detection based on deep learning

2021 ◽  
pp. 002072092098352
Author(s):  
Seokyong Shin ◽  
Hyunho Han ◽  
Sang Hun Lee
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Autonomous Vehicles ◽  
Detection Accuracy ◽  
Small Object ◽  
Feature Maps ◽  
Low Level ◽  
Small Object Detection ◽  
High Level ◽  
Networks Structure

YOLOv3 is a deep learning-based real-time object detector and is mainly used in applications such as video surveillance and autonomous vehicles. In this paper, we proposed an improved YOLOv3 (You Only Look Once version 3) applied Duplex FPN, which enhanced large object detection by utilizing low-level feature information. The conventional YOLOv3 improved the small object detection performance by applying FPN (Feature Pyramid Networks) structure to YOLOv2. However, YOLOv3 with an FPN structure specialized in detecting small objects, so it is difficult to detect large objects. Therefore, this paper proposed an improved YOLOv3 applied Duplex FPN, which can utilize low-level location information in high-level feature maps instead of the existing FPN structure of YOLOv3. This improved the detection accuracy of large objects. Also, an extra detection layer was added to the top-level feature map to prevent failure of detection of parts of large objects. Further, dimension clusters of each detection layer were reassigned to learn quickly how to accurately detect objects. The proposed method was compared and analyzed in the PASCAL VOC dataset. The experimental results showed that the bounding box accuracy of large objects improved owing to the Duplex FPN and extra detection layer, and the proposed method succeeded in detecting large objects that the existing YOLOv3 did not.

scholarly journals Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Haotian Li ◽  
Kezheng Lin ◽  
Jingxuan Bai ◽  
Ao Li ◽  
Jiali Yu
Keyword(s):  
Object Detection ◽  
Detection Rate ◽  
Detection Algorithm ◽  
Single Shot ◽  
Small Object ◽  
Feature Maps ◽  
Scale Invariant ◽  
Feature Pyramid ◽  
Small Object Detection ◽  
Detection And Localization

In order to improve the detection rate of the traditional single-shot multibox detection algorithm in small object detection, a feature-enhanced fusion SSD object detection algorithm based on the pyramid network is proposed. Firstly, the selected multiscale feature layer is merged with the scale-invariant convolutional layer through the feature pyramid network structure; at the same time, the multiscale feature map is separately converted into the channel number using the scale-invariant convolution kernel. Then, the obtained two sets of pyramid-shaped feature layers are further feature fused to generate a set of enhanced multiscale feature maps, and the scale-invariant convolution is performed again on these layers. Finally, the obtained layer is used for detection and localization. The final location coordinates and confidence are output after nonmaximum suppression. Experimental results on the Pascal VOC 2007 and 2012 datasets confirm that there is a 8.2% improvement in mAP compared to the original SSD and some existing algorithms.

scholarly journals SSD-TSEFFM: New SSD Using Trident Feature and Squeeze and Extraction Feature Fusion

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3630 ◽  
Author(s):  
Young-Joon Hwang ◽  
Jin-Gu Lee ◽  
Un-Chul Moon ◽  
Ho-Hyun Park
Keyword(s):  
Object Detection ◽  
Semantic Information ◽  
Feature Fusion ◽  
Contextual Information ◽  
Single Shot ◽  
Small Object ◽  
Dilated Convolution ◽  
Average Improvement ◽  
Proposed Model ◽  
Small Object Detection

The single shot multi-box detector (SSD) exhibits low accuracy in small-object detection; this is because it does not consider the scale contextual information between its layers, and the shallow layers lack adequate semantic information. To improve the accuracy of the original SSD, this paper proposes a new single shot multi-box detector using trident feature and squeeze and extraction feature fusion (SSD-TSEFFM); this detector employs the trident network and the squeeze and excitation feature fusion module. Furthermore, a trident feature module (TFM) is developed, inspired by the trident network, to consider the scale contextual information. The use of this module makes the proposed model robust to scale changes owing to the application of dilated convolution. Further, the squeeze and excitation block feature fusion module (SEFFM) is used to provide more semantic information to the model. The SSD-TSEFFM is compared with the faster regions with convolution neural network features (RCNN) (2015), SSD (2016), and DF-SSD (2020) on the PASCAL VOC 2007 and 2012 datasets. The experimental results demonstrate the high accuracy of the proposed model in small-object detection, in addition to a good overall accuracy. The SSD-TSEFFM achieved 80.4% mAP and 80.2% mAP on the 2007 and 2012 datasets, respectively. This indicates an average improvement of approximately 2% over other models.

scholarly journals SSD-EMB: An Improved SSD Using Enhanced Feature Map Block for Object Detection

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2842
Author(s):  
Hong-Tae Choi ◽  
Ho-Jun Lee ◽  
Hoon Kang ◽  
Sungwook Yu ◽  
Ho-Hyun Park
Keyword(s):  
Object Detection ◽  
Great Success ◽  
Processing Unit ◽  
Single Shot ◽  
Small Object ◽  
Feature Map ◽  
Proposed Model ◽  
Small Object Detection ◽  
Detection Speed ◽  
Good Detection

The development of deep learning has achieved great success in object detection, but small object detection is still a difficult and challenging task in computer vision. To address the problem, we propose an improved single-shot multibox detector (SSD) using enhanced feature map blocks (SSD-EMB). The enhanced feature map block (EMB) consists of attention stream and feature map concatenation stream. The attention stream allows the proposed model to focus on the object regions rather than background owing to channel averaging and the effectiveness of the normalization. The feature map concatenation stream provides additional semantic information to the model without degrading the detection speed. By combining the output of these two streams, the enhanced feature map, which improves the detection of a small object, is generated. Experimental results show that the proposed model has high accuracy in small object detection. The proposed model not only achieves good detection accuracy, but also has a good detection speed. The SSD-EMB achieved a mean average precision (mAP) of 80.4% on the PASCAL VOC 2007 dataset at 30 frames per second on an RTX 2080Ti graphics processing unit, an mAP of 79.9% on the VOC 2012 dataset, and an mAP of 26.6% on the MS COCO dataset.

scholarly journals An Approach to Improve SSD through Skip Connection of Multiscale Feature Maps

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Xiaoguo Zhang ◽  
Ye Gao ◽  
Fei Ye ◽  
Qihan Liu ◽  
Kaixin Zhang
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Semantic Information ◽  
Feature Fusion ◽  
Poor Performance ◽  
Detection Performance ◽  
Single Shot ◽  
Small Object ◽  
Feature Maps ◽  
Input Size

SSD (Single Shot MultiBox Detector) is one of the best object detection algorithms and is able to provide high accurate object detection performance in real time. However, SSD shows relatively poor performance on small object detection because its shallow prediction layer, which is responsible for detecting small objects, lacks enough semantic information. To overcome this problem, SKIPSSD, an improved SSD with a novel skip connection of multiscale feature maps, is proposed in this paper to enhance the semantic information and the details of the prediction layers through skippingly fusing high-level and low-level feature maps. For the detail of the fusion methods, we design two feature fusion modules and multiple fusion strategies to improve the SSD detector’s sensitivity and perception ability. Experimental results on the PASCAL VOC2007 test set demonstrate that SKIPSSD significantly improves the detection performance and outperforms lots of state-of-the-art object detectors. With an input size of 300 × 300, SKIPSSD achieves 79.0% mAP (mean average precision) at 38.7 FPS (frame per second) on a single 1080 GPU, 1.8% higher than the mAP of SSD while still keeping the real-time detection speed.

scholarly journals An Evaluation of Deep Learning Methods for Small Object Detection

2020 ◽  
Vol 2020 ◽  
pp. 1-18 ◽  
Author(s):  
Nhat-Duy Nguyen ◽  
Tien Do ◽  
Thanh Duc Ngo ◽  
Duy-Dinh Le
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
State Of The Art ◽  
Rapid Development ◽  
Empirical Evaluation ◽  
Grid Cell ◽  
Small Object ◽  
Feature Maps ◽  
Comparative Results ◽  
Small Object Detection

Small object detection is an interesting topic in computer vision. With the rapid development in deep learning, it has drawn attention of several researchers with innovations in approaches to join a race. These innovations proposed comprise region proposals, divided grid cell, multiscale feature maps, and new loss function. As a result, performance of object detection has recently had significant improvements. However, most of the state-of-the-art detectors, both in one-stage and two-stage approaches, have struggled with detecting small objects. In this study, we evaluate current state-of-the-art models based on deep learning in both approaches such as Fast RCNN, Faster RCNN, RetinaNet, and YOLOv3. We provide a profound assessment of the advantages and limitations of models. Specifically, we run models with different backbones on different datasets with multiscale objects to find out what types of objects are suitable for each model along with backbones. Extensive empirical evaluation was conducted on 2 standard datasets, namely, a small object dataset and a filtered dataset from PASCAL VOC 2007. Finally, comparative results and analyses are then presented.

scholarly journals Vehicle and Vessel Detection on Satellite Imagery: A Comparative Study on Single-Shot Detectors

2020 ◽  
Vol 12 (7) ◽  
pp. 1217 ◽  
Author(s):  
Tanguy Ophoff ◽  
Steven Puttemans ◽  
Vasileios Kalogirou ◽  
Jean-Philippe Robin ◽  
Toon Goedemé
Keyword(s):  
Object Detection ◽  
Satellite Imagery ◽  
Satellite Data ◽  
Single Shot ◽  
Small Object ◽  
Average Precision ◽  
Vessel Detection ◽  
Speed Up ◽  
Small Object Detection ◽  
The Many

In this paper, we investigate the feasibility of automatic small object detection, such as vehicles and vessels, in satellite imagery with a spatial resolution between 0.3 and 0.5 m. The main challenges of this task are the small objects, as well as the spread in object sizes, with objects ranging from 5 to a few hundred pixels in length. We first annotated 1500 km2, making sure to have equal amounts of land and water data. On top of this dataset we trained and evaluated four different single-shot object detection networks: YOLOV2, YOLOV3, D-YOLO and YOLT, adjusting the many hyperparameters to achieve maximal accuracy. We performed various experiments to better understand the performance and differences between the models. The best performing model, D-YOLO, reached an average precision of 60% for vehicles and 66% for vessels and can process an image of around 1 Gpx in 14 s. We conclude that these models, if properly tuned, can thus indeed be used to help speed up the workflows of satellite data analysts and to create even bigger datasets, making it possible to train even better models in the future.

Sign in / Sign up

Export Citation Format

Share Document